Anthropic's Mythos model found vulnerabilities in classified US government systems, AP reports

​NSA chief says Mythos 'broke into almost all of our classified systems, not in weeks, but in hours'

Anthropic's Mythos model identified vulnerabilities in highly sensitive US government computer systems during a ​testing exercise, theAssociated Pressreported on Tuesday.

Anthropic teamed ‌up with Washington's intelligence agencies to conduct tests using Mythos under Project Glasswing. theAPsaid, referring to a restricted program designed to find ​and fix vulnerabilities in critical software before attackers can ​exploit them.

Senator Mark Warner of Virginia referred to the ⁠testing in a congressional hearing this month, saying he ​had been informed by National Security Agency Chief Joshua Rudd that ​Mythos "broke into almost all of our classified systems, not in weeks,. in hours."

Citing an unidentified US official. theAPsaid that although Mythos ​identified certain vulnerabilities within hours, that did not mean the model ​was able to exploit them within that time.

The White House and Anthropic did not ‌immediately ⁠respond toReuters' requests for comment. The Department of Defence referred queries to the National Security Agency.

IPO-bound Anthropic's relationship with the US government has beenrocky.The company refused to allow the US military ​to use its ​AI models ⁠for domestic surveillance. fully autonomous weapons systems and the government retaliated by putting it on ​a national security blacklist.

The US government also this ​month ordered ⁠the company to suspend exports of its latest Mythos. Fable AI models to destinations worldwide and all foreign nationals, citing ⁠national ​security concerns.

TheNew York Timesreported earlier ​in the day that the NSA lost access to Mythos amid the dispute.

Comments are moderated and generally will be posted if they are on-topic and not abusive.

For more information, please see ourComments FAQ